© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15346
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, or quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IModel
    -1.00
    几个人
    -0.94
     etc
    -0.94
     materials
    -0.88
     شاه
    -0.86
     中古
    -0.86
     Insee
    -0.85
     Sloveniji
    -0.84
    を増
    -0.83
    任何人
    -0.83
    POSITIVE LOGITS
    轻松
    0.82
     poszczegól
    0.79
    ця
    0.79
     нада
    0.76
    voucher
    0.75
    chay
    0.74
     грамм
    0.73
     gewüns
    0.73
     đám
    0.73
     McQueen
    0.72
    Activations Density 0.006%

    No Known Activations